CONTRAST for WSFACTORS (MANOVA: Repeated Measures command)
The levels of a within-subjects factor are represented by different dependent variables. Therefore, contrasts between levels of such a factor compare these dependent variables. Specifying the type of contrast amounts to specifying a transformation to be performed on the dependent variables.
- An orthonormal transformation is automatically performed on the dependent variables in a repeated measures analysis.
- To specify the type of orthonormal transformation,
use the
CONTRAST
subcommand for the within-subjects factors. - Regardless of the contrast type you specify, the transformation matrix is orthonormalized before use.
- If you do not specify a contrast type for within-subjects
factors, the default contrast type is orthogonal
POLYNOMIAL
. Intrinsically orthogonal contrast types are recommended for within-subjects factors if you wish to examine each degree-of-freedom test. Other orthogonal contrast types areDIFFERENCE
andHELMERT
.MULTIV
andAVERF
tests are identical, no matter what contrast was specified. - To perform non-orthogonal contrasts, you must use
the
TRANSFORM
subcommand instead ofCONTRAST
. TheTRANSFORM
subcommand is discussed in TRANSFORM Subcommand (MANOVA: Multivariate command). - When you implicitly request a transformation of the
dependent variables with
CONTRAST
for within-subjects factors, the same transformation is applied to any covariates in the analysis. The number of covariates must be an integer multiple of the number of dependent variables. - You can display the transpose of the transformation
matrix generated by your within-subjects contrast using the keyword
TRANSFORM
on thePRINT
subcommand.
Example
MANOVA SCORE1 SCORE2 SCORE3 BY GROUP(1,4)
/WSFACTORS=ROUND(3)
/CONTRAST(ROUND)=DIFFERENCE
/CONTRAST(GROUP)=DEVIATION
/PRINT=TRANSFORM PARAM(ESTIM).
- This analysis has one between-subjects factor, GROUP, with levels 1, 2, 3, and 4, and one within-subjects factor, ROUND, with three levels that are represented by the three dependent variables.
- The first
CONTRAST
subcommand specifies difference contrasts for ROUND, the within-subjects factor. - There is no
WSDESIGN
subcommand, so a default full factorial within-subjects design is assumed. This could also have been specified asWSDESIGN=ROUND
, or simplyWSDESIGN
. - The second
CONTRAST
subcommand specifies deviation contrasts for GROUP, the between-subjects factor. This subcommand could have been omitted because deviation contrasts are the default. -
PRINT
requests the display of the transformation matrix generated by the within-subjects contrast and the parameter estimates for the model. - There is no
DESIGN
subcommand, so a default full factorial between-subjects design is assumed. This could also have been specified asDESIGN=GROUP
, or simplyDESIGN
.